Triple
T9551043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pearic languages |
E230420
|
entity |
| Predicate | speakerPopulation |
P36744
|
FINISHED |
| Object | very small |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: very small | Statement: [Pearic languages, speakerPopulation, very small]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speakerPopulation Context triple: [Pearic languages, speakerPopulation, very small]
-
A.
haveSpeakerPopulation
chosen
Indicates that an entity has a specified number or population size of people who speak a particular language.
-
B.
typicalNumberOfVoices
Indicates the usual or characteristic number of distinct voices or parts involved in performing or realizing something (such as a musical work or texture).
-
C.
speakerNumber
Indicates the number of distinct speakers involved in a given speech, dialogue, or conversational instance.
-
D.
peopleCountDescriptor
Indicates how the number of people involved in a situation, group, or context is characterized or described.
-
E.
speakerType
Indicates the role or category of a participant in a communicative act (e.g., narrator, quoted speaker, system voice) within a given context.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca847d3be8819099c9dad2a7e786f1 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd991df7308190a56d95f195627513 |
completed | April 1, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69ccd58bd21881908b860e3ee469af13 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:02 p.m.